© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7557
    Prev
    Next
    INDEX
    Explanations

    fear, unhappiness, curiosity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndUpdate
    -0.09
     Ñģвои
    -0.09
    ischen
    -0.09
    ä¸ĢæŶ
    -0.08
     Yong
    -0.08
    uge
    -0.08
    пи
    -0.08
    endance
    -0.08
    ania
    -0.08
    love
    -0.08
    POSITIVE LOGITS
    æŁIJç§į
    0.12
    å·²ä¹ħ
    0.10
    æľīç§į
    0.10
    ä½ķãģĭ
    0.09
    éĢ®
    0.09
    æŃ£åľ¨è¿Ľè¡Į
    0.09
    çĸ¼çĹĽ
    0.09
    åİĨç»ı
    0.09
    ä¿¡æģ¯æľįåĬ¡
    0.09
    æľīæīĢ
    0.08
    Activations Density 0.038%

    No Known Activations